XXXXXXX
                     XXXXXXX
                    XXXXXXXX
                    XXXXXXXX
                    XX      
           XXX       X      
          XX X       X      
         XX  XX      XX     
         X    XXXXXXX X     
        XX          XXX     
        x                   
        x                   
xxx     X                   
XXX    XX                   
XXX  XXX                    
  XX X                      
   XXX                      
 XXX XXX    XXX XXX        XXX      XXX XXX              
XXX   XXX        XXX     XXX XXX    XXX   XXX            
XXX   XXX       XXX     XXX   XXX   XXX   XXX            
XXX   XXX    XXX XXX     XXX XXX    XXX   XXX            
XXX   XXX     XXX       XXX   XXX   XXX   XXX            
XXX   XXX    XXX        XXX   XXX   XXX   XXX            
 XXX XXX      XXX XXX   XXX   XXX   XXX   XXX            

 XXX XXX       XXX      XXX   XXX    XXX XXX    XXX XXX  
XXX   XXX    XXX XXX    XXX   XXX      XXX           XXX 
XXX   XXX   XXX   XXX    XXX XXX       XXX          XXX  
 XXX XXX     XXX XXX       XXX         XXX       XXX XXX 
XXX   XXX   XXX   XXX      XXX         XXX        XXX    
XXX   XXX   XXX   XXX      XXX         XXX       XXX     
 XXX XXX    XXX   XXX      XXX       XXX XXX      XXX XXX
SpotifyInstagramTwitter

+

GitHubLinkedInResume

ozanbayiz [at] berkeley [dot] edu

Ozan Bayiz

I'm a fourth-year undergraduate R&C Scholar at UC Berkeley studying CS. I'm interested in exploring how multimodal signals can be used to enhance understanding and generation of visual data.

I'm very appreciative of Vongani Maluleke’s mentorship as I find my way through CV research.

Ozan Bayiz

Featured Projects

View all projects
  • Personal Website
    2025-08-13
    Personal Website

    Me, online, built with React, Next.js, and Tailwind CSS.

  • Investigating Demographic Attribute Representation in Vision Encoders
    2025-05-11
    Investigating Demographic Attribute Representation in Vision Encoders

    Probed Florence‑2’s DaViT vision encoder with linear classifiers and trained patch‑level SAEs to discover interpretable sparse dictionary features (SDFs).

Research

Coming soon :') like so soon. The soonest

Research placeholder
Ozan Bayiz, 2025